Author name cluster

Manuel Roveri

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic

Hazem Hesham Yousef Shalby
Fabrizio Pittorino
Francesca Palermo
Diana Trojaniello
Manuel Roveri

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic, instance-based mixed-precision quantization promises a superior accuracy-efficiency trade-off by allocating higher precision only when needed. However, a critical bottleneck remains: existing methods require a costly dequantize-to-float and requantize-to-integer cycle to change precision, breaking the integer-only hardware paradigm and compromising performance gains. This paper introduces Dynamic Quantization Training (DQT), a novel framework that removes this bottleneck. At the core of DQT is a nested integer representation where lower-precision values are bit-wise embedded within higher-precision ones. This design, coupled with custom integer-only arithmetic, allows for on-the-fly bit-width switching through a near-zero-cost bit-shift operation. This makes DQT the first quantization framework to enable both dequantization-free static mixed-precision of the backbone network, and truly efficient dynamic, instance-based quantization through a lightweight controller that decides at runtime how to quantize each layer. We demonstrate DQT state-of-the-art performance on ResNet18 on CIFAR-10 and ResNet50 on ImageNet. On ImageNet, our 4-bit dynamic ResNet50 achieves 77.00% top-1 accuracy, an improvement over leading static (LSQ, 76.70%) and dynamic (DQNET, 76.94%) methods at a comparable BitOPs budget. Crucially, DQT achieves this with a bit-width transition cost of only 28.3M simple bit-shift operations, a drastic improvement over the 56.6M costly Multiply-Accumulate (MAC) floating-point operations required by previous dynamic approaches - unlocking a new frontier in efficient, adaptive AI.

PDF Details DOI

AAAI Conference 2026 Conference Paper

InfoQ: Mixed-Precision Quantization via Global Information Flow

Mehmet Emre Akbulut
Hazem Hesham Yousef Shalby
Fabrizio Pittorino
Manuel Roveri

Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a complex combinatorial optimization problem. Current state-of-the-art methods rely on computationally expensive search algorithms or local sensitivity heuristic proxies like the Hessian, which fail to capture the cascading global effects of quantization error. In this work, we argue that the quantization sensitivity of a layer should not be measured by its local properties, but by its impact on the information flow throughout the entire network. We introduce InfoQ, a novel framework for mixed-precision quantization that is training-free in the bit-width search phase. InfoQ assesses layer importance by performing a single forward pass to measure the change in mutual information in the remaining part of the network, thus creating a global sensitivity score. This approach directly quantifies how quantizing one layer degrades the information characteristics of subsequent layers. The resulting scores are used to formulate bit-width allocation as an integer linear programming problem, which is solved efficiently to minimize total sensitivity under a given budget (e.g., model size or BitOps). Our retraining-free search phase provides a superior search-time/accuracy trade-off (using two orders of magnitude less data compared to state-of-the-art methods such as LIMPQ), while yielding up to a 1% accuracy improvement for MobileNetV2 and ResNet18 on ImageNet at high compression rates (14.00x and 10.66x).

PDF Details DOI

ECAI Conference 2025 Conference Paper

NITRO-D: Native Integer-Only Training of Deep Convolutional Neural Networks

Alberto Pirillo
Luca Colombo
Manuel Roveri

Quantization is a pivotal technique for managing the growing computational and memory demands of Deep Neural Networks (DNNs). By reducing the number of bits used to represent weights and activations (typically from 32-bit Floating-Point (FP) to 16-bit or 8-bit integers), quantization reduces memory footprint, energy consumption, and execution time of DNNs. However, most existing methods typically target DNN inference, while training still relies on FP operations, limiting applicability in environments where FP arithmetic is unavailable. To date, only one prior work has addressed integer-only training, and only for Multi-Layer Perceptron (MLP) architectures. This paper introduces NITRO-D, a novel framework for training deep integer-only Convolutional Neural Networks (CNNs) that operate entirely in the integer domain for both training and inference. NITRO-D enables training of integer CNNs without requiring a separate quantization scheme. Specifically, it introduces a novel architecture that integrates multiple local-loss blocks, which include the proposed NITRO-Scaling layer and NITRO-ReLU activation function. The proposed framework also features a novel learning algorithm that employs local error signals and leverages IntegerSGD, an optimizer specifically designed for integer computations. NITRO-D is implemented as an open-source Python library. Extensive evaluations on state-of-the-art image recognition datasets demonstrate its effectiveness. For integer-only MLPs, NITRO-D improves test accuracy by up to +5. 96% over the state-of-the-art. It also successfully trains integer-only CNNs, reducing memory requirements and energy consumption by up to 76. 14% and 32. 42%, respectively, compared to the traditional FP backpropagation algorithm.

Details

UAI Conference 2021 Conference Paper

Time-variant variational transfer for value functions

Giuseppe Canonaco
Andrea Soprani
Matteo Giuliani
Andrea Castelletti
Manuel Roveri
Marcello Restelli

In most of the transfer learning approaches to reinforcement learning (RL) the distribution over the tasks is assumed to be stationary. Therefore, the target and source tasks are i. i. d. samples of the same distribution. Unfortunately, this assumption rarely holds in real-world conditions, e. g. , due to seasonality or periodicity, evolution in the environment or faults in the sensors/actuators. In the context of this work, we consider the problem of transferring value functions through a variational method when the distribution that generates the tasks is time-variant, proposing a solution that leverages this temporal structure inherent in the task generating process. Furthermore, by means of a finite-sample analysis, the previously mentioned solution is theoretically compared to its time-invariant version. Finally, the experimental evaluation of the proposed technique is carried out on the lake Como water system representing a real-world scenario and on three different RL environments with three distinct temporal dynamics.

Details

ECAI Conference 2020 Conference Paper

Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning

Giuseppe Canonaco
Marcello Restelli
Manuel Roveri

In most Reinforcement Learning (RL) studies, the considered task is assumed to be stationary, i. e. , it does not change its behavior or its characteristics over time, as this allows to generate all the convergence properties of RL techniques. Unfortunately, this assumption does not hold in real-world scenarios where systems and environments typically evolve over time. For instance, in robotic applications, sensor or actuator faults would induce a sudden change in the RL settings, while in financial applications the evolution of the market can cause a more gradual variation over time. In this paper, we present an adaptive RL algorithm able to detect changes in the environment or in the reward function and react to these changes by adapting to the new conditions of the task. At first, we develop a figure of merit onto which a hypothesis test can be applied to detect changes between two different learning iterations. Then, we extended this test to sequentially operate over time by means of the CUmulative SUM (CUSUM) approach. Finally, the proposed change-detection mechanism is combined (following an adaptive-active approach) with a well known RL algorithm to make it able to deal with non-stationary tasks. We tested the proposed algorithm on two well-known continuous-control tasks to check its effectiveness in terms of non-stationarity detection and adaptation over a vanilla RL algorithm.

Details

IJCAI Conference 2016 Conference Paper

Change Detection in Multivariate Datastreams: Likelihood and Detectability Loss

Cesare Alippi
Giacomo Boracchi
Diego Carrera
Manuel Roveri

We address the problem of detecting changes in multivariate datastreams, and we investigate the intrinsic difficulty that change-detection methods have to face when the data dimension scales. In particular, we consider a general approach where changes are detected by comparing the distribution of the log-likelihood of the datastream over different time windows. Despite the fact that this approach constitutes the frame of several change-detection methods, its effectiveness when data dimension scales has never been investigated, which is indeed the goal of our paper. We show that the magnitude of the change can be naturally measured by the symmetric Kullback-Leibler divergence between the pre- and post-change distributions, and that the detectability of a change of a given magnitude worsens when the data dimension increases. This problem, which we refer to as detectability loss, is due to the linear relationship between the variance of the log-likelihood and the data dimension. We analytically derive the detectability loss on Gaussian-distributed datastreams, and empirically demonstrate that this problem holds also on real-world datasets and that can be harmful even at low data-dimensions (say, 10).

PDF Details

TAAS Journal 2016 Journal Article

Just-in-Time Adaptive Algorithm for Optimal Parameter Setting in 802.15.4 WSNs

Simone Brienza
Manuel Roveri
Domenico De Guglielmo
Giuseppe Anastasi

Recent studies have shown that the IEEE 802.15.4 MAC protocol suffers from severe limitations, in terms of reliability and energy efficiency, when the CSMA/CA parameter setting is not appropriate. However, selecting the optimal setting that guarantees the application reliability requirements, with minimum energy consumption, is not a trivial task in wireless sensor networks, especially when the operating conditions change over time. In this paper we propose a Just-in-Time LEarning-based Adaptive Parameter tuning (JIT-LEAP) algorithm that adapts the CSMA/CA parameter setting to the time-varying operating conditions by also exploiting the past history to find the most appropriate setting for the current conditions. Following the approach of active adaptive algorithms, the adaptation mechanism of JIT-LEAP is triggered by a change detection test only when needed (i.e., in response to a change in the operating conditions). Simulation results show that the proposed algorithm outperforms other similar algorithms, both in stationary and dynamic scenarios.

Details DOI